System and method for significant image selection using visual tracking

• US 7,573,439 B2
• Filed: 03/10/2005
• Issued: 08/11/2009
• Est. Priority Date: 11/24/2004
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Lau, Denny Wingchung, Yeluri, Vijaykalyan, Morita, Mark M.
• Primary Examiner(s): Lewis; David L
• Application Number:
  US11/077,299
• Publication Number:
  US 20060109238A1
• Time in Patent Office: 1,615 Days
• Field of Search: 345 7- 9, 345/156
• US Class Current: 345/7
• CPC Class Codes: A61B 2017/00216 with eye tracking or head position tracking control
• CPC Class Codes: G06F 3/013 Eye tracking input arrangements G06F3/015 takes precedence
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 40/63 for local operation

Abstract

Certain embodiments of the present invention provide a method and system for improved identification of significant images using visual tracking. Certain embodiments of the system include a visual tracking system capable of tracking a user gaze with respect to a display device and a significant image selector for identifying at least one significant image based on user viewing time. The visual tracking system identifies an image at which a user is gazing records a viewing time during which the user is looking at the image. In an embodiment, the visual tracking system records viewing times for one or more users. In an embodiment, meta-data is associated with one or more significant images to identify the images as significant images, for example. The system may further include a database or table storing significant image information.

Claims

1. A system for visual identification of significant images, said system comprising:

a visual tracking system capable of tracking a user gaze with respect to at least one medical display device, wherein said visual tracking system identifies an image at which a user is gazing and wherein said visual tracking system records a user viewing time during which said user is looking at said image;

a significant image selector for identifying at least one significant image based on said user viewing time;

a medical image database for storing medical images; and

an arbitration module for arbitrating among a plurality of users

wherein significant images are designated as significant in said medical image database.

2. The system of claim 1, wherein said visual tracking system records viewing times for one or more users using the medical imaging system at the same time.

3. The system of claim 1, further comprising a display device capable of displaying images and data.

4. The system of claim 1, further comprising meta-data associated with said at least one significant image, wherein said meta-data identifies said at least one significant image as a significant image.

5. The system of claim 1, further comprising a database or table including significant image information.

6. The system of claim 1, further comprising an authentication module for authenticating a user.

7. A method for improved significant image identification using a computer, said method:

arbitrating among a plurality of viewers to determine at least one user for gaze tracking;

tracking at least one location of a user gaze for said at least one user in relation to a reference position using a tracking system;

identifying at least one image at said at least one location;

recording a viewing time by said at least one user with respect to said image;

designating said at least one image as a significant image based on said viewing time; and

storing images in a medical image database such that significant images are designated as significant in said medical image database.

8. The method of claim 7, wherein said recording step further comprises recording viewing times for a plurality of images.

9. The method of claim 8, wherein said designating step further comprises designating at least one significant image based on viewing times greater than a threshold.

10. The method of claim 8, wherein said designating step further comprises designating at least one significant image based on a predefined number of longest viewing times.

11. The method of claim 7, wherein said designating step further comprises designating said image as a significant image based on a comparison of said viewing time with at least one of a threshold and a second viewing time for a second image.

12. The method of claim 7, further comprising referring said significant image.

18. The method of claim 7, wherein said at least one user is a plurality of users, and said at least one location is a plurality of locations.

13. A computer-readable storage medium including a set of instructions for a computer, the set of instructions comprising:

an arbitration routine for arbitrating conflicts among a plurality of users;

a gaze detection routine for determining an image that a user is viewing;

a timer routine for tracking a viewing time during which said user views said image;

a significant image selection routine for selecting at least one significant image based on said viewing time; and

a storage routine for storing said at least one significant image in a database such that said significant images are designated as significant in said database.

14. The set of instructions of claim 13, wherein said significant image selection routine selects at least one significant image based on at least one of longest viewing time, most frequent viewing time, and most recent viewing time.

15. The set of instructions of claim 13, wherein said significant image selection routine selects at least one significant image based on at least one of viewing times greater than a threshold and a predefined number of longest viewing times.

16. The set of instructions of claim 13, wherein said significant image selection routine modifies meta-data associated with said at least one significant image to identify said at least one significant image.

17. The set of instructions of claim 13, further comprising a referral routine for referring said at least one significant image.